Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1386. Min Range: -4.1386
Max Act: 4.1386. Min Act: -0.1700
Data Index: 6214739 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1386. Min Range: -4.1386
Max Act: 4.0448. Min Act: -0.1700
Data Index: 1221724 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1386. Min Range: -4.1386
Max Act: 4.0136. Min Act: -0.1700
Data Index: 5870370 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1386. Min Range: -4.1386
Max Act: 4.0136. Min Act: -0.1700
Data Index: 6431174 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 4023968 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7686077 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7236607 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7117436 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 8650160 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 8004290 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9510. Min Act: -0.1700
Data Index: 173808 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 2103973 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 3992152 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 2934183 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7599756 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 3631240 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 3475976 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7333549 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 5982302 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1386. Min Range: -4.1386
Max Act: 3.9823. Min Act: -0.1700
Data Index: 610108 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19